Containerizing tasks to ensure robust AI/ML data curation pipelines to estimate environmental disparities in the rural south

将任务容器化，以确保强大的 AI/ML 数据管理管道，以估计南部农村的环境差异

• 批准号: 10842665
• 负责人: Michelle L Bell
• 金额: $ 34.38万
• 依托单位: YALE UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-07-24 至 2024-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10842665
• 关键词: Acceleration; Accounting; Address; Administrative Supplement; Adopted; Adoption; Air Pollution; Architecture; Artificial Intelligence; Cities; Code; Collaborations; Communities; Computer Systems; Data; Data Set; Decentralization; Disparity; Documentation; Engineering; Ensure; Environment; Environmental Health; Ethnic Origin; Exposure to; FAIR principles; Foundations; Goals; Health; Heat Waves; High Performance Computing; High temperature of physical object; Hospitalization; Individual; Institution; Machine Learning; Medicare; Older Population; Outcome; Output; Ownership; Parents; Persons; Play; Population; Process; Race; Readiness; Regulation; Reproducibility; Research; Research Personnel; Rural; Rural Health; Rural Population; Socioeconomic Status; Source; TRUST principles; Testing; United States Centers for Medicare and Medicaid Services; Update; Variant; Virginia; Weather; West Virginia; Work; adverse birth outcomes; base; cold temperature; collaborative environment; community engagement; computerized data processing; computing resources; data analysis pipeline; data cleaning; data curation; data privacy; environmental disparity; environmental health disparity; environmental justice; ethnic minority population; extreme temperature; health data; improved; low socioeconomic status; machine learning pipeline; privacy protection; racial minority population; repository; research data dissemination; rural setting; rurality; urban area; urban setting

Project Summary Our parent R01 addresses a major scientific gap studying how the health of rural populations, including rural racial and ethnic minority groups, is impacted by air pollution and extreme temperature. As part of the parent R01 we are 1) generating a data architecture for air pollution, heat, cold, health, socioeconomic status (SES), urban and rural form, and other factors in Virginia and West Virginia; 2) estimating the disparities in exposure to air pollution and weather (cold, heat, and heat waves) by race/ethnicity, SES, and rurality, accounting for variations in rural form; and 3) estimating the disparities in the associations between exposure to air pollution or weather and health for the very young (adverse birth outcomes) and older populations (hospital admissions for those >65 years), considering differences by various vulnerability factors (low SES, race/ethnicity) and urban/rural form. As part of the parent R01, we have made significant progress in generating a data architecture for air pollution, heat, cold, health, SES, urban/rural form, and other factors. More specifically we have obtained health data from the Centers of Medicare and Medicaid services (CMS). However, while considerable progress has been made in developing data processing pipelines for CMS claims data, the CMS data privacy and confidentiality limitations hinder the sharing of preprocessed datasets, leading to duplication of data cleaning and processing efforts. This duplication of effort can be wasteful, as researchers may not be able to build on each other's work or collaborate effectively. While data cannot be shared, sharing of open processing pipelines is crucial to eliminate duplication efforts and allow for more readily available AI/ML ready data. When workflows are shared containers are critical to ensure reproducibility. With this administrative supplement, our goal is the adoption of containerized data processing tasks to enhance the deployment of AI/ML pipelines for CMS data in the parent R01 and the wider research communities. The use of containers enables the easy exchange or updating of single components in a processing pipeline, which can be reused/recycled across AI/ML pipelines shared by different investigators in the study team and more broadly across research institutions. The adoption of data processing containerized tasks enhances reproducibility of our parent R01 and allows for the optimization of computational resources over High-Performance Computing (HPC). The container-based AI/ML pipelines will accelerate the velocity of research in the parent R01 allowing us to rigorously estimate the disparities in the associations between exposure to air pollution and weather on health outcomes. Furthermore, these improvements are crucial to allow for the dissemination of the workflow pipelines across the wider research community.

项目摘要 我们的父母R01解决了一个主要的科学差距，研究了包括农村在内的农村人口的健康 种族和少数民族群体受到空气污染和极端温度的影响。作为父母的一部分 R01我们是1）生成用于空气污染，热，寒冷，健康，社会经济状况（SES）的数据架构（SES）， 城市和农村形式，以及弗吉尼亚州和西弗吉尼亚州的其他因素； 2）估计暴露差异 通过种族/种族，SES和乡村 农村形式的变化； 3）估计暴露于空气污染之间的关联差异 或年轻（不良出生结果）和较老的人口（住院） 对于那些> 65年），考虑各种脆弱性因素（低SES，种族/种族）和 城市/农村形式。 作为母公司R01的一部分，我们在生成空气污染的数据架构方面取得了重大进展， 热，寒冷，健康，SES，城市/农村形式以及其他因素。更具体地说，我们获得了健康数据 来自Medicare和Medicaid服务（CMS）的中心。但是，尽管取得了很大的进步 为CMS索赔数据，CMS数据隐私和机密性开发数据处理管道而制作 限制阻碍了预处理数据集的共享，从而重复了数据清洁和处理 努力。这种重复的努力可能会浪费，因为研究人员可能无法在彼此的工作上建立 或有效合作。尽管数据无法共享，但共享开放处理管道的共享对于 消除重复工作，并允许更容易获得的AI/ML准备就绪数据。当共享工作流程时 容器对于确保可重复性至关重要。 有了这种管理补充，我们的目标是采用容器化数据处理任务 增强父R01和更广泛的研究中CMS数据的AI/ML管道的部署 社区。容器的使用可以轻松交换或更新单个组件 处理管道，可以在不同研究者共享的AI/ML管道上重复使用/回收 研究团队以及更广泛的研究机构。采用数据处理容器 任务增强了我们的父r01的可重复性，并允许优化计算资源 超出高性能计算（HPC）。 基于容器的AI/ML管道将加速父r01的研究速度，使我们能够 严格估计暴露于空气污染与健康天气之间的关联差异 结果。此外，这些改进对于允许工作流程的传播至关重要 整个更广泛的研究社区的管道。